Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add VoDaiLocz/kilo-kit-mcp --skill graph-raggit clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/graph-rag)<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/graph-rag"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/graph-rag/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/graph-rag"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/graph-rag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.00933 |
| Opus 5 | $0.00022 | $0.00466 |
| Sonnet 5 | $0.00009 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
graph-rag scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GraphRAG Skill
The graph-rag skill provides structured methods for building and querying Knowledge Graphs (KG) from text and code. Unlike standard RAG, which relies on vector similarity, GraphRAG leverages structural relationships between entities to answer complex, multi-hop, and global queries.
When to Use This Skill
- When you need to understand the "big picture" of a massive repository or documentation set.
- When standard semantic search (vector-only) fails to retrieve relevant information for relational or aggregate questions (e.g., "What are the common design patterns used in this project?").
- When you need to trace dependencies across codebases for safe refactoring.
- When you need to generate high-quality summaries of knowledge clusters (communities).
Limitations of Standard Vector-Only RAG
Standard RAG (Retrieval-Augmented Generation) has significant blind spots:
- Global Aggregation: It cannot easily answer questions requiring knowledge synthesis across the entire corpus (e.g., "Summarize all major architectural decisions").
- Relational Depth: Vector similarity often misses multi-hop relationships between disparate files or concepts.
- Information Density: Vector chunking can lose the context of how entities are linked, leading to hallucinated or fragmented answers.
Core Capabilities
1. Entity-Relation Extraction
Ingest unstructured text or source code and transform it into a structured graph:
- Entities: Identify classes, functions, modules, concepts, or business objects.
- Edges: Map interactions (calls, imports, implements, extends, contains).
- Claims: Capture assertions made in docstrings or documentation.
2. Hierarchical Community Summarization (Leiden Algorithm)
Enable global reasoning by creating levels of abstraction:
- Detect communities using the Leiden algorithm to cluster related entities.
- Generate hierarchical summaries for each community.
- Allow the LLM to query these summaries for high-level synthesis rather than searching millions of raw vectors.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 77 lines · 43 tokens per session scan A a2c682278edd
graph-rag is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 933 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications, inspired by Dify and industry best practices.
ai-product
Every product will be AI-powered. The question is whether you'll.
ai-ml
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.